ZSeven-W/openpencil

The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.

What it solves

OpenPencil is an open-source, AI-native vector design tool that allows users to create user interfaces (UI) using natural language prompts. It bridges the gap between conceptual design and production-ready code by automating the layout and styling of vector graphics through AI agents.

How it works

The tool uses a multi-model intelligence system that adapts prompts based on the model's capabilities (e.g., Claude, GPT-4o, Gemini). It employs an orchestrator to break down complex page designs into smaller spatial sub-tasks, which are then handled by concurrent AI agent teams working in parallel. These agents generate designs on an infinite canvas in real-time. Additionally, it includes a built-in MCP (Model Context Protocol) server, allowing external AI agents (like Claude Code or GitHub Copilot) to read and modify design files directly from a terminal.

Who it’s for

It is designed for UI/UX designers, developers, and product managers who want to accelerate the design-to-code workflow using AI, as well as those who prefer a "design-as-code" approach where designs are stored as human-readable JSON files.

Highlights

  • Prompt-to-UI: Generate full page designs from text descriptions with real-time streaming animations.
  • Concurrent Agent Teams: Parallel generation of different page sections (e.g., hero, footer) by multiple agents.
  • Design-as-Code: Uses .op JSON files that are Git-friendly and diffable.
  • Multi-Platform Export: Export designs to React + Tailwind, Vue, Svelte, Flutter, SwiftUI, Jetpack Compose, and more.
  • MCP Server: Enables terminal-based design automation via MCP-compatible agents.
  • Cross-Platform: Built with a Rust core, available as a native desktop app (macOS, Windows, Linux) and a web app.

Related

  • Project
    open-pencil/open-pencil

    OpenPencil is an open‑source, cross‑platform design editor that reads native Figma (`.fig`) and Pencil (`.pen`) files, offers AI‑driven design creation (plug‑in any LLM), and provides a powerful CLI plus an MCP server for headless automation. It ships as a tiny Tauri desktop app and a PWA, supports real‑time WebRTC collaboration, and includes a Vue SDK for embedding custom editors.

  • Project
    nexu-io/open-design

    An open-source, collaborative design agent workspace that lets users connect their own coding agents to create brand-consistent prototypes, decks, and motion graphics.

  • Project
    OpenCoworkAI/open-codesign

    An open-source, local-first desktop app that turns prompts into polished prototypes and assets using any AI model you choose.

  • Project
    oil-oil/draw-ui

    draw‑ui is an AI‑powered skill that helps an LLM agent design a UI from a text brief or existing screenshot and optionally output ready‑to‑use HTML/CSS or WeChat mini‑program code.

  • Project
    gszhangwei/open-spdd

    A CLI tool and methodology that transforms AI coding prompts into structured design contracts using the REASONS Canvas framework to ensure synchronization between design and implementation.